Drilling problems forecast system based on neural network

Год публикации

Optimization, digitalization and robotization of oil and gas technological processes based on the use of artificial intelligence methods are among the prevailing trends of the 21st century.  The drilling industry  is a prime example of these phenomena. The vector of oil and gas drilling is shifting towards complex objects. The improvement of well drilling technologies allows drilling in geological conditions where it was previously impossible. The construction of wells leads to disruption of the natural thermodynamic and stress-strain state of rocks. It is necessary to take into account all the processes occurring in the well and the near-wellbore zone during drilling for the timely recognition of the onset of various complications and accidents. The average time to eliminate complications and accidents is 20-25% of the total well construction time. The task of reducing this indicator is highly relevant. To solve this problem, the most modern technologies are involved, including machine learning algorithms. The main difficulties encountered when using these technologies are the requirements for artificial neural networks for the minimum necessary number of complications or their representable set for the correct "training" of these networks. This report describes how this problem was solved using a full-scale drilling simulator. The drilling simulator makes it possible to recreate a digital twin of a real well and simulate an almost unlimited number of complications of various kinds on it. This approach allows you to create a sample of the required size for the most efficient training and testing of neural network algorithms. Three groups of complications (stuck-pipe or sticking, loss circulation, kick or gas-oil-water occurrence) and standard drilling operations were simulated to minimize the number of false alarms. A total of 86 experiments were modeled, which were then processed using neural network algorithms. The study revealed that the model of an artificial neural network for predicting future manifestations of complications in the form of the "kick or gas-oil-water occurrence", due to its complexity, is trained more efficiently when using not only the input values of drilling parameters, but also the output results of some auxiliary machine learning models. The latest models are trained to solve both regression problems of the indicator function with the model setting to track changes in certain parameters, and the problem of identifying abnormal situations during drilling in real time. When this module trains an artificial neural network model to detect a pre-accident situation of "kick or gas-oil-water occurrence", the following results were obtained for accuracy: accuracy – 0.89, weighted average f1-score – 0.86. The developed system informs the driller about a possible complication with high accuracy, which allows him to avoid it or minimize the consequences.

(SPE Annual Caspian Technical Conference, 21-22 October, Online)

The authors would like to thank management of the Oil and Gas Research Institute of Russian Academy of Sciences for the permission to present and publish this paper based on the results of the project "Development of a high-performance automated system for preventing complications and emergencies during the construction of oil and gas wells on the basis of permanent geological and technological models of deposits using artificial intelligence technology and industrial blockchain to reduce the risks of geological exploration, including offshore projects "under the Agreement with the Ministry of Science and Higher Education of the Russian Federation on the allocation of a subsidy in the form of a grant dated November 22, 2019 No. 075-15-2019-1688, unique project identifier RFMEFI60419X0217.


  1. Abbas et al (2019). Implementing artificial neural networks and support vector machines to predict lost circulation.Egyptian Journal of Petroleum. 10.1016/j.ejpe.2019.06.006.
  2. Adams, A., Parfitt, S., Reeves, T. et al 1993. Casing System Risk Analysis Using Structural Reliability. Paper presented at the SPE/IADC Drilling Conference, Amsterdam, The Netherlands, 22–25 February. SPE-25693-MS. https:// doi.org/10.2118/25693-MS.
  3. Aldamzharov N. N. Prevention of accidents and complications during drilling of branched horizontal boreholes // News of science of Kazakhstan. № 3(133). 2017.
  4. Al-Hameedi, A. T. T., Alkinani, H. H., Dunn-Norman, S., Flori, R. E., Hilgedick, S. A., Amer, A. S., & Alsaba, M.T. (2018). Using Machine Learning to Predict Lost Circulation in the Rumaila Field, Iraq. SPE-191933-MS was presented at SPE Asia Pacific Oil and Gas Conference and Exhibition, 23-25 October, Brisbane, Australia. https:// doi.org/10.2118/191933-MS.
  5. Alkinani, H. H., Al-Hameedi, A. T. T., Dunn-Norman, S., Alkhamis, M. M., and Mutar, R. A. (2019, April 8). Prediction of Lost Circulation Prior to Drilling for Induced Fractures Formations Using Artificial Neural Networks. SPE-195197- MS was presented at SPE Oklahoma City Oil and Gas Symposium, 9-10 April, Oklahoma City, Oklahoma, USA. https://doi.org/10.2118/195197-MS.
  6. Alshaikh, A., Magana-Mora, A., Gharbi, S. A., & Al-Yami, A. (2019, March 22). Machine Learning for Detecting Stuck Pipe Incidents: Data Analytics and Models Evaluation. International Petroleum Technology Conference. doi:10.2523/ IPTC-19394-MS
  7. Antipova, K., Klyuchnikov, N., Zaytsev, A., Gurina, E., Romanenkova, E., & Koroteev, D. (2019, September 23). Data- Driven Model for the Drilling Accidents Prediction. Society of Petroleum Engineers. doi:10.2118/195888-MS
  8. Arnaout, A., Zoellner, P., Thonhauser, G., & Johnstone, N. (2013, October 28). Intelligent Data Quality Control of Real- time Rig Data. Society of Petroleum Engineers. doi:10.2118/167437-MS
  9. Blikra, H., Pia, G., Wessel, J. S., Svendsen, M., Rommetveit, R., & Oedegaard, S. I. (2014, March 4). The Operational Benefit of Testing HPHT/MPD Procedures Using an Advanced Full Scale Drilling Simulator. Society of Petroleum Engineers. doi:10.2118/167958-MS
  10. Dedenuola, D., Iyamu, E., and Adeleye, O. 2003. Stochastic Approach to Kick Tolerance Determination in Risk Based Designs. Paper presented at the SPE Annual Technical Conference and Exhibition, Denver, Colorado, USA, 5–8 October. SPE-84174-MS. https://doi.org/10.2118/84174-MS.
  11. Dmitrievsky A.N., Eremin N.A., Duplyakin V. O., Kapranov V. V. Algorithm for creating a neural network model for classification in systems for preventing complications and emergencies in construction of oil and gas wells. // Sensors & Systems. 2019. № 12 (243). pp.3–10. doi: 10.25728/datsys.2019.12.1
  12. Eremin N.A., Chernikov A.D., Sardanashvili O.N., Stolyarov V.E., Arkhipov A. I. Digital well-building technologies. Creation of a high-performance automated system to prevent complications and emergencies in the process of construction of oil and gas wells. // Business Journal Neftegaz. Ru, No. 4 (100). 2020. pp.38–50. (In Russian).
  13. Ferreira, A. P. L. A., Carvalho, D. J. L., Rodrigues, R. M.. 2015. Automated Decision Support and Expert Collaboration Avoid Stuck Pipe and Improve Drilling Operations in Offshore Brazil Subsalt Well. Presented at the Offshore Technology Conference, Houston, Texas, 4–7 May. OTC-25838. https://doi.org/10.4043/25838-MS.
  14. Geng Z, Wang H, Fan M, et al Predicting seismic-based risk of lost circulation using machine learning. Journal of Petroleum Science and Engineering, 2019, 176:679–688.
  15. Goebel, T., Molina, R.V., Vilalta, R. et al 2014. Method  and  System  for  Predicting a  Drill  String  Stuck  Pipe  Event.  https:// www.google.com/patents/US8752648 Google Patents.
  16. Hempkins, W. B., Kingsborough, R. H., Lohec, W. E. 1987. Multivariate Statistical Analysis of Stuck Drillpipe Situations. SPE Drilling Engineering 2 (03): 237–244. SPE-14181-PA. https://doi.org/10.2118/14181-PA.
  17. Hou, X., Yang, J., Yin, Q., Chen, L., Cao, B., Xu, J., … Zhao, X. (2019, October 21). Automatic Gas Influxes Detection in Offshore Drilling Based on Machine Learning Technology. Society of Petroleum Engineers. doi:10.2118/198534-MS
  18. Jahanbakhshi, R., Keshavarzi, R., Aliyari Shoorehdeli, M., & Emamzadeh, A. (2012, December 1). Intelligent Prediction of Differential Pipe Sticking by Support Vector Machine Compared With Conventional Artificial Neural Networks: An Example of Iranian Offshore Oil Fields. Society of Petroleum Engineers. doi:10.2118/163062-PA
  19. Jahanbakhshi et al (2014) Artificial neural network-based prediction and geomechanical analysis of lost circulation in naturally fractured reservoirs: a case study, European Journal of Environmental and Civil Engineering, 18:3, 320–335, DOI:10.1080/19648189.2013.860924.
  20. Lind, Y. B. and Kabirova, A. R. 2014. Artificial Neural Networks in Drilling Troubles Prediction. Presented at the SPE Russian Oil and Gas Exploration and Production Technical Conference and Exhibition held in Moscow, Russia, 14– 16 October. SPE-171274-MS. https://doi.org/10.2118/171274-MS.
  21. Macpherson, J. D., de Wardt, J. P., Florence, F. et al 2013. Drilling Systems Automation: Current State, Initiatives and Potential Impact. Presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, USA, 30 September–2 October. SPE-166263-MS. https://doi.org/10.2118/166263-MS.
  22. Mason, S. and Chandrasekhar, S. 2005. Stochastic Kick Load Modeling. Paper presented at the SPE High Pressure/High Temperature Sour Well Design Applied Technology Workshop, The Woodlands, Texas, USA, 17–19 May. SPE-97564- MS. https://doi.org/10.2118/97564-MS.
  23. Miri, R., Sampaio, J. H. B., Afshar, M.. 2007. Development of Artificial Neural Networks to Predict Differential Pipe Sticking in Iranian Offshore Oil Fields. Presented at the International Oil Conference and Exhibition in Mexico, Veracruz, Mexico, 27 30 June. SPE-108500-MS. https://doi.org/10.2118/108500-MS.
  24. Moazzeni, A. R., Nabaei, M., and Jegarluei, S. G. (2010). Prediction of Lost Circulation Using Virtual Intelligence in One of Iranian Oilfields. SPE-136992-MS was presented at Nigeria Annual International Conference and Exhibition, 31 July – 7. https://doi.org/10.2118/136992-MS.
  25. Murillo, A., Neuman, J., & Samuel, R. (2009, January 1). Pipe Sticking Prediction and Avoidance Using Adaptive Fuzzy Logic Modeling. Society of Petroleum Engineers. doi:10.2118/120128-MS
  26. Naraghi, M. E., Ezzatyar, P., and Jamshidi, S. 2013. Prediction of Drilling Pipe Sticking by Active Learning Method (ALM). Journal of Petroleum and Gas Engineering 4 (07): 173–183. EBB3D3041956. https://doi.org/10.5897/ JPGE2013.0166.
  27. Noshi, C. I., & Schubert, J. J. (2018, October 5). The Role of Machine Learning in Drilling Operations; A Review. Society of Petroleum Engineers. doi:10.2118/191823-18ERM-MS
  28. Odegard, S. I., Risvik, B. T., Bjorkevoll, K. S., Mehus, O., Rommetveit, R., & Svendsen, M. (2013, March 5). Advanced Dynamic Training Simulator For Drilling As Well As Related Experience From Training Of Drilling Teams With Focus On Realistic Downhole Feedback. Society of Petroleum Engineers. doi:10.2118/163510-MS
  29. Peng, Q., Fan, H., Xu, S., Zhou, H., Lai, M., Ma, G., & Fu, S. (2014, November 12). A Real-Time Warning System for Identifying Drilling Accidents. Society of Petroleum Engineers. doi:10.2118/172303-MS
  30. Podgornov V. M., Efimenko N. S. Technology of drilling wells in permafrost rocks // Quality Management in the oil and gas complex. 2017. no. 1. Pp. 59–61.
  31. Rodrigues G. da Silva, F., de Souza Cruz, M., Barduchi, B., Bellumat, E., Vieira dos Santos, M., Barroso de Matos, V.,… Leibsohn Martins, A. (2020, July 20). Six Years Operating a Real Time Drilling Problem Detection Software in Deepwater Environments: Results and Challenges. Society of Petroleum Engineers. doi:10.2118/199077-MS
  32. Rommetveit, R., Bjorkevoll, K. S., Halsey, G. wesley, Fjar, E., Odegaard, S. I., Herbert, M. C., … Larsen, B. (2007, January 1). e-Drilling: A System for Real-Time Drilling Simulation, 3D Visualization and Control. Society of Petroleum Engineers. doi:10.2118/106903-MS
  33. Sabah, M., Talebkeikhah, M., Agin, F., Telebkeikhah, F., Hasheminasab, E., Application of decision tree, artificial neural networks, and adaptive neuro-fuzzy inference system on predicting lost circulation: A case study from Marun oil field, Journal of Petroleum Science and Engineering (2019), doi: https://doi.org/10.1016/j.petrol.2019.02.045.
  34. Salminen, K., Cheatham, C., Smith, M., & Valiullin, K. (2017, September 1). Stuck-Pipe Prediction by Use of Automated Real-Time Modeling and Data Analysis. Society of Petroleum Engineers. doi:10.2118/178888-PA
  35. Shaker, S. S., & Reynolds, D. J. (2020, May 4). Kicks and Blowouts Prediction Before and During Drilling in the Over- Pressured Sediments. Offshore Technology Conference. doi:10.4043/30711-MS
  36. Tallin, A., Paslay, P., Cernocky, E. et al 2000. Risk Assessment of Exploration Well Designs in the Oman Ara Salt. Paper presented at the SPE Annual Technical Conference and Exhibition, Dallas, Texas, USA, 1–4 October. SPE-63130- MS. https://doi.org/10.2118/63130-MS.
  37. Tang, H. Y., Gang, W., Rommetveit, R., Chusov, A., Helgeland, S., & Namork, L. (2016, August 22). Advanced Drilling Simulation and Engineering Center Provide Support for Challenging Drilling Operations in the South China Sea. Society of Petroleum Engineers. doi:10.2118/180685-MS
  38. Unrau, S., Torrione, P., Hibbard, M. et al 2017. Machine Learning Algorithms Applied to Detection of Well Control Events. Presented at the SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition, Dammam, Saudi Arabia, 24–27 April. SPE-188104-MS. http://dx.doi.org/10.2118/188104-MS.
  39. Varshavskiy  et  al,   2017.   Application   of   classification   and   clustering   methods   to   improve   the   efficiency  of case systems. International journal "Programmnye produkty i sistemy," 36, pp.625–631. http:// dx.doi.org/10.15827/0236-235x.120.625-631.
  40. Weakley, R. R. (1990, January 1). Use of Stuck Pipe Statistics To Reduce the Occurrence of Stuck Pipe. Society of Petroleum Engineers. doi:10.2118/20410-MS
  41. Wylie, W. and Visram, A. 1990. Drilling Kick Statistics. Paper presented at the SPE/IADC Drilling Conference, Houston, Texas, USA, 27 February–2 March. SPE-19914-MS. https://doi.org/10.2118/19914-MS.
  42. Yang, J., Sun, T., Zhao, Y., Borujeni, A. T., Shi, H., & Yang, H. (2019, July 15). Advanced Real-Time Gas Kick Detection Using Machine Learning Technology. International Society of Offshore and Polar Engineers.
  43. Yin, Q., Yang, J., Borujeni, A. T., Shi, S., Sun, T., Yang, Y., … Zhao, X. (2019, July 15). Intelligent Early Kick Detection in Ultra-Deepwater High-Temperature High-Pressure (HPHT) Wells Based on Big Data Technology. International Society of Offshore and Polar Engineers.
  44. Zhang, F., Islam, A., Zeng, H., Chen, Z., Zeng, Y., Wang, X., & Li, S. (2019, November 11). Real Time Stuck Pipe Prediction by Using a Combination of Physics-Based Model and Data Analytics Approach. Society of Petroleum Engineers. doi:10.2118/197167-MS.